Français
3. Sources of parallelism and fundamental operations
3.1 Data parallelism
In data parallelism, the same operation is carried out simultaneously by several processors on different data. This definition covers two notions: the presence of data parallelism and the way in which this parallelism is exploited.
Let's take a simple example from linear algebra, and more specifically from matrix calculus. The addition of two matrices consists in adding all the elements of the same index of the two operand matrices and placing the result in the element of the same index of the result matrix. Here's the corresponding loop for operand matrices B and C and result matrix A :
The Ultimate Scientific and Technical Reference
This article is included in
Software technologies and System architectures
This offer includes:
Knowledge Base
Updated and enriched with articles validated by our scientific committees
Services
A set of exclusive tools to complement the resources
Practical Path
Operational and didactic, to guarantee the acquisition of transversal skills
Doc & Quiz
Interactive articles with quizzes, for constructive reading
Sources of parallelism and fundamental operations
Parallelism in monoprocessors
Bibliography
The Ultimate Scientific and Technical Reference
